A model for learning systems

Authors:
Reid G. Smith;Tom M. Mitchell;Richard A. Chestek;Bruce G. Buchanan
Affiliations:
Departments of Computer Science and Electrical Engineering, Stanford University, Stanford, California;Departments of Computer Science and Electrical Engineering, Stanford University, Stanford, California;Departments of Computer Science and Electrical Engineering, Stanford University, Stanford, California;Departments of Computer Science and Electrical Engineering, Stanford University, Stanford, California
Venue:
IJCAI'77 Proceedings of the 5th international joint conference on Artificial intelligence - Volume 1
Year:
1977

Citing 9
Cited 4

On machine intelligence (2nd ed.)

On machine intelligence (2nd ed.)
Some studies in machine learning using the game of checkers

Computers & thought
Pattern recognition by machine

Computers & thought
A pattern-recognition program that generates, evaluates, and adjusts its own operators

Computers & thought
The simulation of verbal learning behavior

Computers & thought
Steps toward artificial intelligence

Computers & thought
Artificial Intelligence

Artificial Intelligence
A Computational Model of Skill Acquisition

A Computational Model of Skill Acquisition
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)

Constrained example generation: a testbed for studying issues in learning

IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 1
Learning to control a dynamic physical system

AAAI'87 Proceedings of the sixth National conference on Artificial intelligence - Volume 2
Learning to control a dynamic physical system

AAAI'87 Proceedings of the sixth National conference on Artificial intelligence - Volume 2
Learning Bayesian nets that perform well

UAI'97 Proceedings of the Thirteenth conference on Uncertainty in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

A model for learning systems is presented, and representative AI, pattern recognition, and control systems are discussed in terms of its framework. The model details the functional components felt to be essential for any learning system, independent of the techniques used for its construction, and the specific environment in which it operates. These components are Performance element, instance selector, critic, earning element, blackboard, and world model. Consideration of learning system design leads naturally to the concept of a layered system, each layer operating at a different level of abstraction.